Abstract

The Data reflects Humans as most of the data is online. Privacy for individual’s data has become a prime concern. Securing and preserving that privacy has been a focus for long decades. In data analytics, machine learning and data science analysis over users’ private data utilize to understand the individual user’s responses to present data publicly. The issue with private data presented online that consisted of personal private data was sensitive and confidential was a significant issue, so a particular group of mathematicians and cryptographers came together to resolve this issue by introducing the concept of Differential Privacy. Differential privacy is assurance over information privacy without damaging the chance of having privacy risk by including some amount of Random noise in the form of robust data to the original dataset. Differential privacy is also a tool with an algorithm that helps maintain Privacy by Preserving and Randomizing data responses— measuring the accuracy of statistical data by performing analysis. To perform this process of differential privacy, IBM developed an open-sourced algorithm called Diffprivlib [1]. With this library, the project has created a Front-End Web application that can perform data analysis that involves different mechanisms, models, and Tools. This project is an attempt to integrate all mechanisms, models, and tools involved in DiffPrivLib [1]. The primary purpose of this paper is to showcase the work on differential privacy that consists in developing a user-friendly web application that can be open-sourced. This application is designed in a python programming package and will experiment with the dataset to perform the analysis to show the impact of differential privacy algorithms on different values on epsilon with accuracy and privacy.

Published in: International Journal of Innovative Science and Research Technology IJISRT– August 2021 (Volume 6 – Issue 8).